Browsing by Author "Lin C"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Development of a cross-sectoral antimicrobial resistance capability assessment framework.
    (BMJ Publishing Group, 2024-02-05) Ferdinand AS; McEwan C; Lin C; Betham K; Kandan K; Tamolsaian G; Pugeva B; McKenzie J; Browning G; Gilkerson J; Coppo M; James R; Peel T; Levy S; Townell N; Jenney A; Stewardson A; Cameron D; Macintyre A; Buising K; Howden BP; Biswas S
    Antimicrobial resistance (AMR) is an urgent and growing global health concern, and a clear understanding of existing capacities to address AMR, particularly in low-income and middle-income countries (LMICs), is needed to inform national priorities, investment targets and development activities. Across LMICs, there are limited data regarding existing mechanisms to address AMR, including national AMR policies, current infection prevention and antimicrobial prescribing practices, antimicrobial use in animals, and microbiological testing capacity for AMR. Despite the development of numerous individual tools designed to inform policy formulation and implementation or surveillance interventions to address AMR, there is an unmet need for easy-to-use instruments that together provide a detailed overview of AMR policy, practice and capacity. This paper describes the development of a framework comprising five assessment tools which provide a detailed assessment of country capacity to address AMR within both the human and animal health sectors. The framework is flexible to meet the needs of implementers, as tools can be used separately to assess the capacity of individual institutions or as a whole to align priority-setting and capacity-building with AMR National Action Plans (NAPs) or national policies. Development of the tools was conducted by a multidisciplinary team across three phases: (1) review of existing tools; (2) adaptation of existing tools; and (3) piloting, refinement and finalisation. The framework may be best used by projects which aim to build capacity and foster cross-sectoral collaborations towards the surveillance of AMR, and by LMICs wishing to conduct their own assessments to better understand capacity and capabilities to inform future investments or the implementation of NAPs for AMR.
  • Thumbnail Image
    Item
    WBNet: Weakly-supervised salient object detection via scribble and pseudo-background priors
    (Elsevier Ltd, 2024-10) Wang Y; Wang R; He X; Lin C; Wang T; Jia Q; Fan X
    Weakly supervised salient object detection (WSOD) methods endeavor to boost sparse labels to get more salient cues in various ways. Among them, an effective approach is using pseudo labels from multiple unsupervised self-learning methods, but inaccurate and inconsistent pseudo labels could ultimately lead to detection performance degradation. To tackle this problem, we develop a new multi-source WSOD framework, WBNet, that can effectively utilize pseudo-background (non-salient region) labels combined with scribble labels to obtain more accurate salient features. We first design a comprehensive salient pseudo-mask generator from multiple self-learning features. Then, we pioneer the exploration of generating salient pseudo-labels via point-prompted and box-prompted Segment Anything Models (SAM). Then, WBNet leverages a pixel-level Feature Aggregation Module (FAM), a mask-level Transformer-decoder (TFD), and an auxiliary Boundary Prediction Module (EPM) with a hybrid loss function to handle complex saliency detection tasks. Comprehensively evaluated with state-of-the-art methods on five widely used datasets, the proposed method significantly improves saliency detection performance. The code and results are publicly available at https://github.com/yiwangtz/WBNet.